Proposed Model for Context Topic Identification of English and Hindi News Article Through LDA Approach with NLP Technique

According to the survey, India has world's second-largest newspaper market, with more than 100 K outlets, approx 240 million circulation, and 1300 subscribers or readers. The topic modeling work is increasing day by day, researchers have published multiple papers implemented them in different areas like software engineering, political science medical, etc. LDA used this research because it been introduced successfully for classification measures probability of a text-dependent on bag-of-words scheme without considering word series. common algorithm excellent implementation Gensim Python package. However, challenge how extract good quality topics that are simple, separated, meaningful. purpose deals finding main same category news articles which two languages (Hindi English) then classifying these language similarity measurement. In research, corpus constructed bigram. To achieve goal, we first build headline link extractor scrap top from Google News feeds both English Hindi (Google collects stories appeared website already accessible 35 over last 30 days) analyses headlines similar.